{"id":"W1978954330","doi":"10.1198/0003130043277","title":"Bootstrap Methods for Developing Predictive Models","year":2004,"lang":"en","type":"article","venue":"The American Statistician","topic":"Hydrology and Drought Analysis","field":"Environmental Science","cited_by":620,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"","keywords":"Resampling; Feature selection; Model selection; Computer science; Statistics; Predictive modelling; Selection (genetic algorithm); Bootstrap aggregating; Variables; Machine learning; Econometrics; Artificial intelligence; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003553103,0.0001005357,0.0001815439,0.00002000263,0.0002474012,0.0000114421,0.0002238543,0.00001691408,0.0000697531],"category_scores_gemma":[0.0000680084,0.000071624,0.00004860015,0.0002776659,0.000711503,0.00007993823,0.00005986656,0.0000768824,0.00006205683],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001201646,"about_ca_system_score_gemma":0.00002497679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001382654,"about_ca_topic_score_gemma":0.0002855738,"domain_scores_codex":[0.9991741,0.0001124416,0.0001448554,0.0002119835,0.00009485089,0.0002618085],"domain_scores_gemma":[0.9993488,0.000294053,0.0001205277,0.000182587,0.000007601126,0.00004644114],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003372935,0.0001069763,0.001961472,0.000009118893,0.0003765118,0.00001325365,0.006941964,0.4291057,0.002251995,0.08609217,0.002073311,0.4707302],"study_design_scores_gemma":[0.0004403414,0.0003614759,0.0214465,0.000007424278,0.0002247071,0.000009034681,0.0008415794,0.1293499,0.001227286,0.8417782,0.003972767,0.0003407157],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0213008,0.00001497221,0.9730555,0.00115404,0.00003043284,0.0001637885,0.00002848215,0.00003192077,0.004220013],"genre_scores_gemma":[0.5878313,0.000009874397,0.410531,0.001470619,0.00002203521,0.00004431793,0.000005883106,0.000008767274,0.00007624539],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7556861,"threshold_uncertainty_score":0.2920742,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03567676071956769,"score_gpt":0.3619012094975819,"score_spread":0.3262244487780143,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}